Predictive Microservice Handoff for 5G Edge Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current handover mechanisms in wireless networks, especially in the transition to 5G, face challenges with workload variances and increased complexity, leading to potential loss of connectivity and poor user experience due to high latency and signaling overhead, particularly in scenarios requiring rapid communication handoffs and high bandwidth.
Innovation Solution
A method for predictively deploying microservices on edge devices using a machine learning model to determine the probability of microservice requests and select suitable edge devices based on compute capacity and workload, ensuring optimal operational service and reducing deployment time, thereby optimizing handover processes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If current handover mechanisms are used in 5G networks, then connectivity can be maintained, but latency increases and signaling overhead grows due to the complex resource allocation and negotiation process
Solution Approach 1:
The patent pre-positions microservices on edge devices before handover events occur. By using machine learning to predict which microservices will be needed and placing them in advance on appropriate edge devices, the system eliminates the delay of deploying services during handover, thus reducing latency while maintaining connectivity.
Solution Approach 2:
The patent segments the network into multiple edge devices distributed across different locations, each capable of running microservices independently. This segmentation allows handover to occur between edge devices without requiring complex centralized resource allocation, thereby reducing signaling overhead and latency.
2Reliability
If current handover mechanisms are used in 5G networks, then connectivity can be maintained, but signaling overhead increases due to the complex resource allocation and negotiation process
Solution Approach 1:
The system performs service placement decisions in advance, before handover events. Machine learning models predict future microservice needs and pre-configure edge devices accordingly, eliminating the need for complex real-time signaling during handover events.
Solution Approach 2:
The patent introduces an intermediary service placement system that uses machine learning to make intelligent decisions about microservice deployment. This intermediary layer abstracts the complexity from the handover process itself, reducing signaling overhead by making placement decisions based on predictions rather than real-time negotiations.
3Loss of time
If microservices are deployed on edge devices in advance, then handover latency is reduced, but network complexity increases due to predictive deployment mechanisms
Solution Approach 1:
The system employs machine learning models that automatically analyze network conditions, user behavior patterns, and service requirements to make autonomous decisions about microservice placement. This self-service capability reduces the need for complex manual configuration and centralized control, managing network complexity through automation.
Solution Approach 2:
The patent changes the parameters used for service placement from static, rule-based criteria to dynamic, machine learning-driven predictions. By continuously adapting placement decisions based on changing network conditions and user behavior, the system reduces handover latency while managing complexity through intelligent parameter adjustment.
Data Source
AI summary
Microservices are predictively deployed on edge devices in a network. An application is run on a client device, the application comprising a set of microservices runnable on any edge device in a set of two or more edge devices. A state of the client device at a first time is determined, the state including one or more microservices currently being run for the client device, and for each microservice currently being run, an edge device running the microservice. One or more microservices that are likely to be run at a second time subsequent to the first time and a location of the client device at the second time are predicted. Based on the predicted location, a next edge device in the set of edge devices is determined for running the one or more microservices predicted to be run at the second time.